Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5b70d72464cde302c3e2ec3b9d4a94c78eba5c04733d75d31fc5f9aa567b47
+oid sha256:97802f8ea7e48d528a43529470da096ba2eb1dca1d4ec44fbb328c85f1059706
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07acb8a0ec1e1a86f1326944109e21dee6f1a920501f0f646fe70a4b1317f160
+oid sha256:126c9d9d6374572323d0bd66f2e964d707b95af2c3b611ab0751328e0ab60ccb
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c801932c815e2dcc3488b72de19c071ccf4b093291a73d876fa8173f60b868d4
+oid sha256:98928e1126863039d68d24c31d1f4b445df92b7d2d85fd2e0a5ab706a5eed5d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003904057780055145,
+  "epoch": 0.0005856086670082717,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.734,
       "step": 18
+    },
+    {
+      "epoch": 0.0004099260669057902,
+      "grad_norm": 1.6760863065719604,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5574,
+      "step": 21
+    },
+    {
+      "epoch": 0.00046848693360661736,
+      "grad_norm": 1.477821707725525,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.7224,
+      "step": 24
+    },
+    {
+      "epoch": 0.00046848693360661736,
+      "eval_loss": 1.6640890836715698,
+      "eval_runtime": 2819.7792,
+      "eval_samples_per_second": 7.65,
+      "eval_steps_per_second": 3.825,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005270478003074446,
+      "grad_norm": 1.10930335521698,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.6077,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005856086670082717,
+      "grad_norm": 1.6078771352767944,
+      "learning_rate": 0.0,
+      "loss": 1.6078,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7511608746049536.0,
+  "total_flos": 1.1313781074296832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null